Multi-User Activity Recognition in a Smart Home
作者： Liang Wang , Tao Gu , Xianping Tao , Hanhua Chen , Jian Lu
DOI: 10.2991/978-94-91216-05-3_3
关键词:
摘要: The advances of wearable sensors and wireless networks offer many opportunities to recognize human activities from sensor readings in pervasive computing. Existing work so far focus mainly on recognizing a single user home environment. However, there are typically multiple inhabitants real they often perform together. In this paper, we investigate the problem multi-user using setting. We develop multi-modal, platform collect data for users, study two temporal probabilistic models—Coupled Hidden Markov Model (CHMM) Factorial Conditional Random Field (FCRF)—to model interacting processes sensor-based, scenario. conduct real-world trace collection done by subjects over weeks, evaluate these models through our experimental studies. Our results show that achieve an accuracy 96.41% with CHMM 87.93% FCRF, respectively, activities.
core.ac.uk
springer.com
springerlink.com参考文章(42)
Jane Yung-Jen Hsu, Chia-Chun Lian, Chatting activity recognition in social occasions using factorial conditional random fields with iterative classification national conference on artificial intelligence. pp. 1814- 1815 ,(2008)
Matthai Philipose, Danny Wyatt, Tanzeem Choudhury, Unsupervised activity recognition using automatically mined common sense national conference on artificial intelligence. pp. 21- 27 ,(2005)
Parisa Rashidi, G. Michael Youngblood, Diane J. Cook, Sajal K. Das, Inhabitant guidance of smart environments international conference on human computer interaction. pp. 910- 919 ,(2007) , 10.1007/978-3-540-73107-8_100
Emmanuel Munguia Tapia, Stephen S. Intille, Kent Larson, Activity Recognition in the Home Using Simple and Ubiquitous Sensors Lecture Notes in Computer Science. pp. 158- 175 ,(2004) , 10.1007/978-3-540-24646-6_10
Donald J. Patterson, Lin Liao, Dieter Fox, Henry Kautz, Inferring High-Level Behavior from Low-Level Sensors ubiquitous computing. pp. 73- 89 ,(2003) , 10.1007/978-3-540-39653-6_6
Tâm Huỳnh, Ulf Blanke, Bernt Schiele, Scalable recognition of daily activities with wearable sensors location and context awareness. pp. 50- 67 ,(2007) , 10.1007/978-3-540-75160-1_4
Keki B. Irani, Usama M. Fayyad, Multi-Interval Discretization of Continuous-Valued Attributes for Classification Learning international joint conference on artificial intelligence. ,vol. 2, pp. 1022- 1027 ,(1993)
Henry Kautz, Jeff Bilmes, Danny Wyatt, Tanzeem Choudhury, A privacy-sensitive approach to modeling multi-person conversations international joint conference on artificial intelligence. pp. 1769- 1775 ,(2007)
Stephen Intille, Matthai Philipose, Emmanuel Munguia Tapia, Jennifer Healey, Beth Logan, A long-term evaluation of sensing modalities for activity recognition ubiquitous computing. pp. 483- 500 ,(2007) , 10.5555/1771592.1771620
D. H. Wilson, C. Atkeson, Simultaneous Tracking and Activity Recognition (STAR) Using Many Anonymous, Binary Sensors Lecture Notes in Computer Science. pp. 62- 79 ,(2005) , 10.1007/11428572_5